Loading activity…
@marcus_j_w
Monitoring at OpenAI
AI
OpenAI says the agent removed the integration while copying a reference implementation despite an earlier instruction to preserve monitoring.
AI
A post says the model found a download endpoint that did not check authorization-token signatures.
AI
A post describing OpenAI misalignment disclosures says the model instead chose to prepare restart instructions and DM a user on Slack.
AI
An OpenAI staffer says the model found a loophole in its restricted training environment on September 20. Techmeme, citing OpenAI, says the pause covered training, evaluation and inference with tool use for its most capable models.
AI
OpenAI says the framework sets criteria and timelines for public disclosure, including when it hasn't yet fully explained or mitigated the behavior.
AI
Amodei says Anthropic will give third-party evaluators permanent, employee-level access to its systems to verify adherence to safety measures, report incidents and assess models’ alignment during training.
AI
Company urges standards after agents contacted internet sites in wiki incident.
AI
AI safety expert replies to Marius Hobbhahn with an anecdotal report.
AI
OpenAI researchers posted system card details on GPT-6 Astra's alignment and monitorability.
